Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-01-29

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Teach verifier dead code removal, this also allows for optimizing /
   removing conditional branches around dead code and to shrink the
   resulting image. Code store constrained architectures like nfp would
   have hard time doing this at JIT level, from Jakub.

2) Add JMP32 instructions to BPF ISA in order to allow for optimizing
   code generation for 32-bit sub-registers. Evaluation shows that this
   can result in code reduction of ~5-20% compared to 64 bit-only code
   generation. Also add implementation for most JITs, from Jiong.

3) Add support for __int128 types in BTF which is also needed for
   vmlinux's BTF conversion to work, from Yonghong.

4) Add a new command to bpftool in order to dump a list of BPF-related
   parameters from the system or for a specific network device e.g. in
   terms of available prog/map types or helper functions, from Quentin.

5) Add AF_XDP sock_diag interface for querying sockets from user
   space which provides information about the RX/TX/fill/completion
   rings, umem, memory usage etc, from Björn.

6) Add skb context access for skb_shared_info->gso_segs field, from Eric.

7) Add support for testing flow dissector BPF programs by extending
   existing BPF_PROG_TEST_RUN infrastructure, from Stanislav.

8) Split BPF kselftest's test_verifier into various subgroups of tests
   in order better deal with merge conflicts in this area, from Jakub.

9) Add support for queue/stack manipulations in bpftool, from Stanislav.

10) Document BTF, from Yonghong.

11) Dump supported ELF section names in libbpf on program load
    failure, from Taeung.

12) Silence a false positive compiler warning in verifier's BTF
    handling, from Peter.

13) Fix help string in bpftool's feature probing, from Prashant.

14) Remove duplicate includes in BPF kselftests, from Yue.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 364 insertions, 86 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 25b3ee85066e..c8bfbbfdfcc3 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1083,12 +1083,17 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 
 /* Arithmatic Operation */
 static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
-			     const u8 rn, struct jit_ctx *ctx, u8 op) {
+			     const u8 rn, struct jit_ctx *ctx, u8 op,
+			     bool is_jmp64) {
 	switch (op) {
 	case BPF_JSET:
-		emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
-		emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
-		emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
+		if (is_jmp64) {
+			emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
+			emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
+			emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
+		} else {
+			emit(ARM_ANDS_R(ARM_IP, rt, rn), ctx);
+		}
 		break;
 	case BPF_JEQ:
 	case BPF_JNE:
@@ -1096,18 +1101,25 @@ static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
 	case BPF_JGE:
 	case BPF_JLE:
 	case BPF_JLT:
-		emit(ARM_CMP_R(rd, rm), ctx);
-		_emit(ARM_COND_EQ, ARM_CMP_R(rt, rn), ctx);
+		if (is_jmp64) {
+			emit(ARM_CMP_R(rd, rm), ctx);
+			/* Only compare low halve if high halve are equal. */
+			_emit(ARM_COND_EQ, ARM_CMP_R(rt, rn), ctx);
+		} else {
+			emit(ARM_CMP_R(rt, rn), ctx);
+		}
 		break;
 	case BPF_JSLE:
 	case BPF_JSGT:
 		emit(ARM_CMP_R(rn, rt), ctx);
-		emit(ARM_SBCS_R(ARM_IP, rm, rd), ctx);
+		if (is_jmp64)
+			emit(ARM_SBCS_R(ARM_IP, rm, rd), ctx);
 		break;
 	case BPF_JSLT:
 	case BPF_JSGE:
 		emit(ARM_CMP_R(rt, rn), ctx);
-		emit(ARM_SBCS_R(ARM_IP, rd, rm), ctx);
+		if (is_jmp64)
+			emit(ARM_SBCS_R(ARM_IP, rd, rm), ctx);
 		break;
 	}
 }
@@ -1615,6 +1627,17 @@ exit:
 	case BPF_JMP | BPF_JLT | BPF_X:
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP | BPF_JSLE | BPF_X:
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
 		/* Setup source registers */
 		rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
 		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
@@ -1641,6 +1664,17 @@ exit:
 	case BPF_JMP | BPF_JLE | BPF_K:
 	case BPF_JMP | BPF_JSLT | BPF_K:
 	case BPF_JMP | BPF_JSLE | BPF_K:
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
 		if (off == 0)
 			break;
 		rm = tmp2[0];
@@ -1652,7 +1686,8 @@ go_jmp:
 		rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 		/* Check for the condition */
-		emit_ar_r(rd[0], rd[1], rm, rn, ctx, BPF_OP(code));
+		emit_ar_r(rd[0], rd[1], rm, rn, ctx, BPF_OP(code),
+			  BPF_CLASS(code) == BPF_JMP);
 
 		/* Setup JUMP instruction */
 		jmp_offset = bpf2a32_offset(i+off, i, ctx);
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index f4e58bcdaa43..13a05f759552 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -62,6 +62,7 @@
 #define ARM_INST_ADDS_I		0x02900000
 
 #define ARM_INST_AND_R		0x00000000
+#define ARM_INST_ANDS_R		0x00100000
 #define ARM_INST_AND_I		0x02000000
 
 #define ARM_INST_BIC_R		0x01c00000
@@ -172,6 +173,7 @@
 #define ARM_ADC_I(rd, rn, imm)	_AL3_I(ARM_INST_ADC, rd, rn, imm)
 
 #define ARM_AND_R(rd, rn, rm)	_AL3_R(ARM_INST_AND, rd, rn, rm)
+#define ARM_ANDS_R(rd, rn, rm)	_AL3_R(ARM_INST_ANDS, rd, rn, rm)
 #define ARM_AND_I(rd, rn, imm)	_AL3_I(ARM_INST_AND, rd, rn, imm)
 
 #define ARM_BIC_R(rd, rn, rm)	_AL3_R(ARM_INST_BIC, rd, rn, rm)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 1542df00b23c..aaddc0217e73 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -362,7 +362,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
-	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+	const bool is64 = BPF_CLASS(code) == BPF_ALU64 ||
+			  BPF_CLASS(code) == BPF_JMP;
 	const bool isdw = BPF_SIZE(code) == BPF_DW;
 	u8 jmp_cond;
 	s32 jmp_offset;
@@ -559,7 +560,17 @@ emit_bswap_uxt:
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP | BPF_JSGE | BPF_X:
 	case BPF_JMP | BPF_JSLE | BPF_X:
-		emit(A64_CMP(1, dst, src), ctx);
+	case BPF_JMP32 | BPF_JEQ | BPF_X:
+	case BPF_JMP32 | BPF_JGT | BPF_X:
+	case BPF_JMP32 | BPF_JLT | BPF_X:
+	case BPF_JMP32 | BPF_JGE | BPF_X:
+	case BPF_JMP32 | BPF_JLE | BPF_X:
+	case BPF_JMP32 | BPF_JNE | BPF_X:
+	case BPF_JMP32 | BPF_JSGT | BPF_X:
+	case BPF_JMP32 | BPF_JSLT | BPF_X:
+	case BPF_JMP32 | BPF_JSGE | BPF_X:
+	case BPF_JMP32 | BPF_JSLE | BPF_X:
+		emit(A64_CMP(is64, dst, src), ctx);
 emit_cond_jmp:
 		jmp_offset = bpf2a64_offset(i + off, i, ctx);
 		check_imm19(jmp_offset);
@@ -601,7 +612,8 @@ emit_cond_jmp:
 		emit(A64_B_(jmp_cond, jmp_offset), ctx);
 		break;
 	case BPF_JMP | BPF_JSET | BPF_X:
-		emit(A64_TST(1, dst, src), ctx);
+	case BPF_JMP32 | BPF_JSET | BPF_X:
+		emit(A64_TST(is64, dst, src), ctx);
 		goto emit_cond_jmp;
 	/* IF (dst COND imm) JUMP off */
 	case BPF_JMP | BPF_JEQ | BPF_K:
@@ -614,12 +626,23 @@ emit_cond_jmp:
 	case BPF_JMP | BPF_JSLT | BPF_K:
 	case BPF_JMP | BPF_JSGE | BPF_K:
 	case BPF_JMP | BPF_JSLE | BPF_K:
-		emit_a64_mov_i(1, tmp, imm, ctx);
-		emit(A64_CMP(1, dst, tmp), ctx);
+	case BPF_JMP32 | BPF_JEQ | BPF_K:
+	case BPF_JMP32 | BPF_JGT | BPF_K:
+	case BPF_JMP32 | BPF_JLT | BPF_K:
+	case BPF_JMP32 | BPF_JGE | BPF_K:
+	case BPF_JMP32 | BPF_JLE | BPF_K:
+	case BPF_JMP32 | BPF_JNE | BPF_K:
+	case BPF_JMP32 | BPF_JSGT | BPF_K:
+	case BPF_JMP32 | BPF_JSLT | BPF_K:
+	case BPF_JMP32 | BPF_JSGE | BPF_K:
+	case BPF_JMP32 | BPF_JSLE | BPF_K:
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_CMP(is64, dst, tmp), ctx);
 		goto emit_cond_jmp;
 	case BPF_JMP | BPF_JSET | BPF_K:
-		emit_a64_mov_i(1, tmp, imm, ctx);
-		emit(A64_TST(1, dst, tmp), ctx);
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		emit_a64_mov_i(is64, tmp, imm, ctx);
+		emit(A64_TST(is64, dst, tmp), ctx);
 		goto emit_cond_jmp;
 	/* function call */
 	case BPF_JMP | BPF_CALL:
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 19a8834e0398..f9513ad38fa6 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -337,6 +337,7 @@
 #define PPC_INST_DIVWU			0x7c000396
 #define PPC_INST_DIVD			0x7c0003d2
 #define PPC_INST_RLWINM			0x54000000
+#define PPC_INST_RLWINM_DOT		0x54000001
 #define PPC_INST_RLWIMI			0x50000000
 #define PPC_INST_RLDICL			0x78000000
 #define PPC_INST_RLDICR			0x78000004
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index c2d5192ed64f..549e9490ff2a 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -165,6 +165,10 @@
 #define PPC_RLWINM(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \
 					___PPC_RS(a) | __PPC_SH(i) |	      \
 					__PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RLWINM_DOT(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM_DOT |	      \
+					___PPC_RA(d) | ___PPC_RS(a) |	      \
+					__PPC_SH(i) | __PPC_MB(mb) |	      \
+					__PPC_ME(me))
 #define PPC_RLWIMI(d, a, i, mb, me)	EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \
 					___PPC_RS(a) | __PPC_SH(i) |	      \
 					__PPC_MB(mb) | __PPC_ME(me))
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 7ce57657d3b8..15bba765fa79 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -768,36 +768,58 @@ emit_clear:
 		case BPF_JMP | BPF_JGT | BPF_X:
 		case BPF_JMP | BPF_JSGT | BPF_K:
 		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP32 | BPF_JGT | BPF_K:
+		case BPF_JMP32 | BPF_JGT | BPF_X:
+		case BPF_JMP32 | BPF_JSGT | BPF_K:
+		case BPF_JMP32 | BPF_JSGT | BPF_X:
 			true_cond = COND_GT;
 			goto cond_branch;
 		case BPF_JMP | BPF_JLT | BPF_K:
 		case BPF_JMP | BPF_JLT | BPF_X:
 		case BPF_JMP | BPF_JSLT | BPF_K:
 		case BPF_JMP | BPF_JSLT | BPF_X:
+		case BPF_JMP32 | BPF_JLT | BPF_K:
+		case BPF_JMP32 | BPF_JLT | BPF_X:
+		case BPF_JMP32 | BPF_JSLT | BPF_K:
+		case BPF_JMP32 | BPF_JSLT | BPF_X:
 			true_cond = COND_LT;
 			goto cond_branch;
 		case BPF_JMP | BPF_JGE | BPF_K:
 		case BPF_JMP | BPF_JGE | BPF_X:
 		case BPF_JMP | BPF_JSGE | BPF_K:
 		case BPF_JMP | BPF_JSGE | BPF_X:
+		case BPF_JMP32 | BPF_JGE | BPF_K:
+		case BPF_JMP32 | BPF_JGE | BPF_X:
+		case BPF_JMP32 | BPF_JSGE | BPF_K:
+		case BPF_JMP32 | BPF_JSGE | BPF_X:
 			true_cond = COND_GE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JLE | BPF_K:
 		case BPF_JMP | BPF_JLE | BPF_X:
 		case BPF_JMP | BPF_JSLE | BPF_K:
 		case BPF_JMP | BPF_JSLE | BPF_X:
+		case BPF_JMP32 | BPF_JLE | BPF_K:
+		case BPF_JMP32 | BPF_JLE | BPF_X:
+		case BPF_JMP32 | BPF_JSLE | BPF_K:
+		case BPF_JMP32 | BPF_JSLE | BPF_X:
 			true_cond = COND_LE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JEQ | BPF_K:
 		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP32 | BPF_JEQ | BPF_K:
+		case BPF_JMP32 | BPF_JEQ | BPF_X:
 			true_cond = COND_EQ;
 			goto cond_branch;
 		case BPF_JMP | BPF_JNE | BPF_K:
 		case BPF_JMP | BPF_JNE | BPF_X:
+		case BPF_JMP32 | BPF_JNE | BPF_K:
+		case BPF_JMP32 | BPF_JNE | BPF_X:
 			true_cond = COND_NE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP32 | BPF_JSET | BPF_K:
+		case BPF_JMP32 | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
 			/* Fall through */
 
@@ -809,18 +831,44 @@ cond_branch:
 			case BPF_JMP | BPF_JLE | BPF_X:
 			case BPF_JMP | BPF_JEQ | BPF_X:
 			case BPF_JMP | BPF_JNE | BPF_X:
+			case BPF_JMP32 | BPF_JGT | BPF_X:
+			case BPF_JMP32 | BPF_JLT | BPF_X:
+			case BPF_JMP32 | BPF_JGE | BPF_X:
+			case BPF_JMP32 | BPF_JLE | BPF_X:
+			case BPF_JMP32 | BPF_JEQ | BPF_X:
+			case BPF_JMP32 | BPF_JNE | BPF_X:
 				/* unsigned comparison */
-				PPC_CMPLD(dst_reg, src_reg);
+				if (BPF_CLASS(code) == BPF_JMP32)
+					PPC_CMPLW(dst_reg, src_reg);
+				else
+					PPC_CMPLD(dst_reg, src_reg);
 				break;
 			case BPF_JMP | BPF_JSGT | BPF_X:
 			case BPF_JMP | BPF_JSLT | BPF_X:
 			case BPF_JMP | BPF_JSGE | BPF_X:
 			case BPF_JMP | BPF_JSLE | BPF_X:
+			case BPF_JMP32 | BPF_JSGT | BPF_X:
+			case BPF_JMP32 | BPF_JSLT | BPF_X:
+			case BPF_JMP32 | BPF_JSGE | BPF_X:
+			case BPF_JMP32 | BPF_JSLE | BPF_X:
 				/* signed comparison */
-				PPC_CMPD(dst_reg, src_reg);
+				if (BPF_CLASS(code) == BPF_JMP32)
+					PPC_CMPW(dst_reg, src_reg);
+				else
+					PPC_CMPD(dst_reg, src_reg);
 				break;
 			case BPF_JMP | BPF_JSET | BPF_X:
-				PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg);
+			case BPF_JMP32 | BPF_JSET | BPF_X:
+				if (BPF_CLASS(code) == BPF_JMP) {
+					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
+						    src_reg);
+				} else {
+					int tmp_reg = b2p[TMP_REG_1];
+
+					PPC_AND(tmp_reg, dst_reg, src_reg);
+					PPC_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0,
+						       31);
+				}
 				break;
 			case BPF_JMP | BPF_JNE | BPF_K:
 			case BPF_JMP | BPF_JEQ | BPF_K:
@@ -828,43 +876,87 @@ cond_branch:
 			case BPF_JMP | BPF_JLT | BPF_K:
 			case BPF_JMP | BPF_JGE | BPF_K:
 			case BPF_JMP | BPF_JLE | BPF_K:
+			case BPF_JMP32 | BPF_JNE | BPF_K:
+			case BPF_JMP32 | BPF_JEQ | BPF_K:
+			case BPF_JMP32 | BPF_JGT | BPF_K:
+			case BPF_JMP32 | BPF_JLT | BPF_K:
+			case BPF_JMP32 | BPF_JGE | BPF_K:
+			case BPF_JMP32 | BPF_JLE | BPF_K:
+			{
+				bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32;
+
 				/*
 				 * Need sign-extended load, so only positive
 				 * values can be used as imm in cmpldi
 				 */
-				if (imm >= 0 && imm < 32768)
-					PPC_CMPLDI(dst_reg, imm);
-				else {
+				if (imm >= 0 && imm < 32768) {
+					if (is_jmp32)
+						PPC_CMPLWI(dst_reg, imm);
+					else
+						PPC_CMPLDI(dst_reg, imm);
+				} else {
 					/* sign-extending load */
 					PPC_LI32(b2p[TMP_REG_1], imm);
 					/* ... but unsigned comparison */
-					PPC_CMPLD(dst_reg, b2p[TMP_REG_1]);
+					if (is_jmp32)
+						PPC_CMPLW(dst_reg,
+							  b2p[TMP_REG_1]);
+					else
+						PPC_CMPLD(dst_reg,
+							  b2p[TMP_REG_1]);
 				}
 				break;
+			}
 			case BPF_JMP | BPF_JSGT | BPF_K:
 			case BPF_JMP | BPF_JSLT | BPF_K:
 			case BPF_JMP | BPF_JSGE | BPF_K:
 			case BPF_JMP | BPF_JSLE | BPF_K:
+			case BPF_JMP32 | BPF_JSGT | BPF_K:
+			case BPF_JMP32 | BPF_JSLT | BPF_K:
+			case BPF_JMP32 | BPF_JSGE | BPF_K:
+			case BPF_JMP32 | BPF_JSLE | BPF_K:
+			{
+				bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32;
+
 				/*
 				 * signed comparison, so any 16-bit value
 				 * can be used in cmpdi
 				 */
-				if (imm >= -32768 && imm < 32768)
-					PPC_CMPDI(dst_reg, imm);
-				else {
+				if (imm >= -32768 && imm < 32768) {
+					if (is_jmp32)
+						PPC_CMPWI(dst_reg, imm);
+					else
+						PPC_CMPDI(dst_reg, imm);
+				} else {
 					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_CMPD(dst_reg, b2p[TMP_REG_1]);
+					if (is_jmp32)
+						PPC_CMPW(dst_reg,
+							 b2p[TMP_REG_1]);
+					else
+						PPC_CMPD(dst_reg,
+							 b2p[TMP_REG_1]);
 				}
 				break;
+			}
 			case BPF_JMP | BPF_JSET | BPF_K:
+			case BPF_JMP32 | BPF_JSET | BPF_K:
 				/* andi does not sign-extend the immediate */
 				if (imm >= 0 && imm < 32768)
 					/* PPC_ANDI is _only/always_ dot-form */
 					PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
 				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
-						    b2p[TMP_REG_1]);
+					int tmp_reg = b2p[TMP_REG_1];
+
+					PPC_LI32(tmp_reg, imm);
+					if (BPF_CLASS(code) == BPF_JMP) {
+						PPC_AND_DOT(tmp_reg, dst_reg,
+							    tmp_reg);
+					} else {
+						PPC_AND(tmp_reg, dst_reg,
+							tmp_reg);
+						PPC_RLWINM_DOT(tmp_reg, tmp_reg,
+							       0, 0, 31);
+					}
 				}
 				break;
 			}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 3ff758eeb71d..ce9defdff62a 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1110,103 +1110,141 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		mask = 0xf000; /* j */
 		goto branch_oc;
 	case BPF_JMP | BPF_JSGT | BPF_K: /* ((s64) dst > (s64) imm) */
+	case BPF_JMP32 | BPF_JSGT | BPF_K: /* ((s32) dst > (s32) imm) */
 		mask = 0x2000; /* jh */
 		goto branch_ks;
 	case BPF_JMP | BPF_JSLT | BPF_K: /* ((s64) dst < (s64) imm) */
+	case BPF_JMP32 | BPF_JSLT | BPF_K: /* ((s32) dst < (s32) imm) */
 		mask = 0x4000; /* jl */
 		goto branch_ks;
 	case BPF_JMP | BPF_JSGE | BPF_K: /* ((s64) dst >= (s64) imm) */
+	case BPF_JMP32 | BPF_JSGE | BPF_K: /* ((s32) dst >= (s32) imm) */
 		mask = 0xa000; /* jhe */
 		goto branch_ks;
 	case BPF_JMP | BPF_JSLE | BPF_K: /* ((s64) dst <= (s64) imm) */
+	case BPF_JMP32 | BPF_JSLE | BPF_K: /* ((s32) dst <= (s32) imm) */
 		mask = 0xc000; /* jle */
 		goto branch_ks;
 	case BPF_JMP | BPF_JGT | BPF_K: /* (dst_reg > imm) */
+	case BPF_JMP32 | BPF_JGT | BPF_K: /* ((u32) dst_reg > (u32) imm) */
 		mask = 0x2000; /* jh */
 		goto branch_ku;
 	case BPF_JMP | BPF_JLT | BPF_K: /* (dst_reg < imm) */
+	case BPF_JMP32 | BPF_JLT | BPF_K: /* ((u32) dst_reg < (u32) imm) */
 		mask = 0x4000; /* jl */
 		goto branch_ku;
 	case BPF_JMP | BPF_JGE | BPF_K: /* (dst_reg >= imm) */
+	case BPF_JMP32 | BPF_JGE | BPF_K: /* ((u32) dst_reg >= (u32) imm) */
 		mask = 0xa000; /* jhe */
 		goto branch_ku;
 	case BPF_JMP | BPF_JLE | BPF_K: /* (dst_reg <= imm) */
+	case BPF_JMP32 | BPF_JLE | BPF_K: /* ((u32) dst_reg <= (u32) imm) */
 		mask = 0xc000; /* jle */
 		goto branch_ku;
 	case BPF_JMP | BPF_JNE | BPF_K: /* (dst_reg != imm) */
+	case BPF_JMP32 | BPF_JNE | BPF_K: /* ((u32) dst_reg != (u32) imm) */
 		mask = 0x7000; /* jne */
 		goto branch_ku;
 	case BPF_JMP | BPF_JEQ | BPF_K: /* (dst_reg == imm) */
+	case BPF_JMP32 | BPF_JEQ | BPF_K: /* ((u32) dst_reg == (u32) imm) */
 		mask = 0x8000; /* je */
 		goto branch_ku;
 	case BPF_JMP | BPF_JSET | BPF_K: /* (dst_reg & imm) */
+	case BPF_JMP32 | BPF_JSET | BPF_K: /* ((u32) dst_reg & (u32) imm) */
 		mask = 0x7000; /* jnz */
-		/* lgfi %w1,imm (load sign extend imm) */
-		EMIT6_IMM(0xc0010000, REG_W1, imm);
-		/* ngr %w1,%dst */
-		EMIT4(0xb9800000, REG_W1, dst_reg);
+		if (BPF_CLASS(insn->code) == BPF_JMP32) {
+			/* llilf %w1,imm (load zero extend imm) */
+			EMIT6_IMM(0xc0010000, REG_W1, imm);
+			/* nr %w1,%dst */
+			EMIT2(0x1400, REG_W1, dst_reg);
+		} else {
+			/* lgfi %w1,imm (load sign extend imm) */
+			EMIT6_IMM(0xc0010000, REG_W1, imm);
+			/* ngr %w1,%dst */
+			EMIT4(0xb9800000, REG_W1, dst_reg);
+		}
 		goto branch_oc;
 
 	case BPF_JMP | BPF_JSGT | BPF_X: /* ((s64) dst > (s64) src) */
+	case BPF_JMP32 | BPF_JSGT | BPF_X: /* ((s32) dst > (s32) src) */
 		mask = 0x2000; /* jh */
 		goto branch_xs;
 	case BPF_JMP | BPF_JSLT | BPF_X: /* ((s64) dst < (s64) src) */
+	case BPF_JMP32 | BPF_JSLT | BPF_X: /* ((s32) dst < (s32) src) */
 		mask = 0x4000; /* jl */
 		goto branch_xs;
 	case BPF_JMP | BPF_JSGE | BPF_X: /* ((s64) dst >= (s64) src) */
+	case BPF_JMP32 | BPF_JSGE | BPF_X: /* ((s32) dst >= (s32) src) */
 		mask = 0xa000; /* jhe */
 		goto branch_xs;
 	case BPF_JMP | BPF_JSLE | BPF_X: /* ((s64) dst <= (s64) src) */
+	case BPF_JMP32 | BPF_JSLE | BPF_X: /* ((s32) dst <= (s32) src) */
 		mask = 0xc000; /* jle */
 		goto branch_xs;
 	case BPF_JMP | BPF_JGT | BPF_X: /* (dst > src) */
+	case BPF_JMP32 | BPF_JGT | BPF_X: /* ((u32) dst > (u32) src) */
 		mask = 0x2000; /* jh */
 		goto branch_xu;
 	case BPF_JMP | BPF_JLT | BPF_X: /* (dst < src) */
+	case BPF_JMP32 | BPF_JLT | BPF_X: /* ((u32) dst < (u32) src) */
 		mask = 0x4000; /* jl */
 		goto branch_xu;
 	case BPF_JMP | BPF_JGE | BPF_X: /* (dst >= src) */
+	case BPF_JMP32 | BPF_JGE | BPF_X: /* ((u32) dst >= (u32) src) */
 		mask = 0xa000; /* jhe */
 		goto branch_xu;
 	case BPF_JMP | BPF_JLE | BPF_X: /* (dst <= src) */
+	case BPF_JMP32 | BPF_JLE | BPF_X: /* ((u32) dst <= (u32) src) */
 		mask = 0xc000; /* jle */
 		goto branch_xu;
 	case BPF_JMP | BPF_JNE | BPF_X: /* (dst != src) */
+	case BPF_JMP32 | BPF_JNE | BPF_X: /* ((u32) dst != (u32) src) */
 		mask = 0x7000; /* jne */
 		goto branch_xu;
 	case BPF_JMP | BPF_JEQ | BPF_X: /* (dst == src) */
+	case BPF_JMP32 | BPF_JEQ | BPF_X: /* ((u32) dst == (u32) src) */
 		mask = 0x8000; /* je */
 		goto branch_xu;
 	case BPF_JMP | BPF_JSET | BPF_X: /* (dst & src) */
+	case BPF_JMP32 | BPF_JSET | BPF_X: /* ((u32) dst & (u32) src) */
+	{
+		bool is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
+
 		mask = 0x7000; /* jnz */
-		/* ngrk %w1,%dst,%src */
-		EMIT4_RRF(0xb9e40000, REG_W1, dst_reg, src_reg);
+		/* nrk or ngrk %w1,%dst,%src */
+		EMIT4_RRF((is_jmp32 ? 0xb9f40000 : 0xb9e40000),
+			  REG_W1, dst_reg, src_reg);
 		goto branch_oc;
 branch_ks:
 		/* lgfi %w1,imm (load sign extend imm) */
 		EMIT6_IMM(0xc0010000, REG_W1, imm);
-		/* cgrj %dst,%w1,mask,off */
-		EMIT6_PCREL(0xec000000, 0x0064, dst_reg, REG_W1, i, off, mask);
+		/* crj or cgrj %dst,%w1,mask,off */
+		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
+			    dst_reg, REG_W1, i, off, mask);
 		break;
 branch_ku:
 		/* lgfi %w1,imm (load sign extend imm) */
 		EMIT6_IMM(0xc0010000, REG_W1, imm);
-		/* clgrj %dst,%w1,mask,off */
-		EMIT6_PCREL(0xec000000, 0x0065, dst_reg, REG_W1, i, off, mask);
+		/* clrj or clgrj %dst,%w1,mask,off */
+		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
+			    dst_reg, REG_W1, i, off, mask);
 		break;
 branch_xs:
-		/* cgrj %dst,%src,mask,off */
-		EMIT6_PCREL(0xec000000, 0x0064, dst_reg, src_reg, i, off, mask);
+		/* crj or cgrj %dst,%src,mask,off */
+		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064),
+			    dst_reg, src_reg, i, off, mask);
 		break;
 branch_xu:
-		/* clgrj %dst,%src,mask,off */
-		EMIT6_PCREL(0xec000000, 0x0065, dst_reg, src_reg, i, off, mask);
+		/* clrj or clgrj %dst,%src,mask,off */
+		EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065),
+			    dst_reg, src_reg, i, off, mask);
 		break;
 branch_oc:
 		/* brc mask,jmp_off (branch instruction needs 4 bytes) */
 		jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
 		EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
 		break;
+	}
 	default: /* too complex, give up */
 		pr_err("Unknown opcode %02x\n", insn->code);
 		return -1;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5542303c43d9..afabf597c855 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -881,20 +881,41 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_JSLT | BPF_X:
 		case BPF_JMP | BPF_JSGE | BPF_X:
 		case BPF_JMP | BPF_JSLE | BPF_X:
+		case BPF_JMP32 | BPF_JEQ | BPF_X:
+		case BPF_JMP32 | BPF_JNE | BPF_X:
+		case BPF_JMP32 | BPF_JGT | BPF_X:
+		case BPF_JMP32 | BPF_JLT | BPF_X:
+		case BPF_JMP32 | BPF_JGE | BPF_X:
+		case BPF_JMP32 | BPF_JLE | BPF_X:
+		case BPF_JMP32 | BPF_JSGT | BPF_X:
+		case BPF_JMP32 | BPF_JSLT | BPF_X:
+		case BPF_JMP32 | BPF_JSGE | BPF_X:
+		case BPF_JMP32 | BPF_JSLE | BPF_X:
 			/* cmp dst_reg, src_reg */
-			EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39,
-			      add_2reg(0xC0, dst_reg, src_reg));
+			if (BPF_CLASS(insn->code) == BPF_JMP)
+				EMIT1(add_2mod(0x48, dst_reg, src_reg));
+			else if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			EMIT2(0x39, add_2reg(0xC0, dst_reg, src_reg));
 			goto emit_cond_jmp;
 
 		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP32 | BPF_JSET | BPF_X:
 			/* test dst_reg, src_reg */
-			EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85,
-			      add_2reg(0xC0, dst_reg, src_reg));
+			if (BPF_CLASS(insn->code) == BPF_JMP)
+				EMIT1(add_2mod(0x48, dst_reg, src_reg));
+			else if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			EMIT2(0x85, add_2reg(0xC0, dst_reg, src_reg));
 			goto emit_cond_jmp;
 
 		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP32 | BPF_JSET | BPF_K:
 			/* test dst_reg, imm32 */
-			EMIT1(add_1mod(0x48, dst_reg));
+			if (BPF_CLASS(insn->code) == BPF_JMP)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
 			EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
 			goto emit_cond_jmp;
 
@@ -908,8 +929,21 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_JSLT | BPF_K:
 		case BPF_JMP | BPF_JSGE | BPF_K:
 		case BPF_JMP | BPF_JSLE | BPF_K:
+		case BPF_JMP32 | BPF_JEQ | BPF_K:
+		case BPF_JMP32 | BPF_JNE | BPF_K:
+		case BPF_JMP32 | BPF_JGT | BPF_K:
+		case BPF_JMP32 | BPF_JLT | BPF_K:
+		case BPF_JMP32 | BPF_JGE | BPF_K:
+		case BPF_JMP32 | BPF_JLE | BPF_K:
+		case BPF_JMP32 | BPF_JSGT | BPF_K:
+		case BPF_JMP32 | BPF_JSLT | BPF_K:
+		case BPF_JMP32 | BPF_JSGE | BPF_K:
+		case BPF_JMP32 | BPF_JSLE | BPF_K:
 			/* cmp dst_reg, imm8/32 */
-			EMIT1(add_1mod(0x48, dst_reg));
+			if (BPF_CLASS(insn->code) == BPF_JMP)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
 
 			if (is_imm8(imm32))
 				EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 8f6cc71e0848..0d9cdffce6ac 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2072,7 +2072,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JSGT | BPF_X:
 		case BPF_JMP | BPF_JSLE | BPF_X:
 		case BPF_JMP | BPF_JSLT | BPF_X:
-		case BPF_JMP | BPF_JSGE | BPF_X: {
+		case BPF_JMP | BPF_JSGE | BPF_X:
+		case BPF_JMP32 | BPF_JEQ | BPF_X:
+		case BPF_JMP32 | BPF_JNE | BPF_X:
+		case BPF_JMP32 | BPF_JGT | BPF_X:
+		case BPF_JMP32 | BPF_JLT | BPF_X:
+		case BPF_JMP32 | BPF_JGE | BPF_X:
+		case BPF_JMP32 | BPF_JLE | BPF_X:
+		case BPF_JMP32 | BPF_JSGT | BPF_X:
+		case BPF_JMP32 | BPF_JSLE | BPF_X:
+		case BPF_JMP32 | BPF_JSLT | BPF_X:
+		case BPF_JMP32 | BPF_JSGE | BPF_X: {
+			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
 			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
@@ -2081,25 +2092,35 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			if (dstk) {
 				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
 				      STACK_VAR(dst_lo));
-				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
-				      STACK_VAR(dst_hi));
+				if (is_jmp64)
+					EMIT3(0x8B,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EDX),
+					      STACK_VAR(dst_hi));
 			}
 
 			if (sstk) {
 				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
 				      STACK_VAR(src_lo));
-				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX),
-				      STACK_VAR(src_hi));
+				if (is_jmp64)
+					EMIT3(0x8B,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EBX),
+					      STACK_VAR(src_hi));
 			}
 
-			/* cmp dreg_hi,sreg_hi */
-			EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
-			EMIT2(IA32_JNE, 2);
+			if (is_jmp64) {
+				/* cmp dreg_hi,sreg_hi */
+				EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+				EMIT2(IA32_JNE, 2);
+			}
 			/* cmp dreg_lo,sreg_lo */
 			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
 			goto emit_cond_jmp;
 		}
-		case BPF_JMP | BPF_JSET | BPF_X: {
+		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP32 | BPF_JSET | BPF_X: {
+			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
 			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
@@ -2108,15 +2129,21 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			if (dstk) {
 				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
 				      STACK_VAR(dst_lo));
-				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
-				      STACK_VAR(dst_hi));
+				if (is_jmp64)
+					EMIT3(0x8B,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EDX),
+					      STACK_VAR(dst_hi));
 			}
 
 			if (sstk) {
 				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
 				      STACK_VAR(src_lo));
-				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX),
-				      STACK_VAR(src_hi));
+				if (is_jmp64)
+					EMIT3(0x8B,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EBX),
+					      STACK_VAR(src_hi));
 			}
 			/* and dreg_lo,sreg_lo */
 			EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
@@ -2126,32 +2153,39 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
 			goto emit_cond_jmp;
 		}
-		case BPF_JMP | BPF_JSET | BPF_K: {
-			u32 hi;
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP32 | BPF_JSET | BPF_K: {
+			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
 			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 			u8 sreg_lo = IA32_ECX;
 			u8 sreg_hi = IA32_EBX;
+			u32 hi;
 
 			if (dstk) {
 				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
 				      STACK_VAR(dst_lo));
-				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
-				      STACK_VAR(dst_hi));
+				if (is_jmp64)
+					EMIT3(0x8B,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EDX),
+					      STACK_VAR(dst_hi));
 			}
-			hi = imm32 & (1<<31) ? (u32)~0 : 0;
 
 			/* mov ecx,imm32 */
-			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
-			/* mov ebx,imm32 */
-			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+			EMIT2_off32(0xC7, add_1reg(0xC0, sreg_lo), imm32);
 
 			/* and dreg_lo,sreg_lo */
 			EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
-			/* and dreg_hi,sreg_hi */
-			EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
-			/* or dreg_lo,dreg_hi */
-			EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+			if (is_jmp64) {
+				hi = imm32 & (1 << 31) ? (u32)~0 : 0;
+				/* mov ebx,imm32 */
+				EMIT2_off32(0xC7, add_1reg(0xC0, sreg_hi), hi);
+				/* and dreg_hi,sreg_hi */
+				EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
+				/* or dreg_lo,dreg_hi */
+				EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+			}
 			goto emit_cond_jmp;
 		}
 		case BPF_JMP | BPF_JEQ | BPF_K:
@@ -2163,29 +2197,44 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JSGT | BPF_K:
 		case BPF_JMP | BPF_JSLE | BPF_K:
 		case BPF_JMP | BPF_JSLT | BPF_K:
-		case BPF_JMP | BPF_JSGE | BPF_K: {
-			u32 hi;
+		case BPF_JMP | BPF_JSGE | BPF_K:
+		case BPF_JMP32 | BPF_JEQ | BPF_K:
+		case BPF_JMP32 | BPF_JNE | BPF_K:
+		case BPF_JMP32 | BPF_JGT | BPF_K:
+		case BPF_JMP32 | BPF_JLT | BPF_K:
+		case BPF_JMP32 | BPF_JGE | BPF_K:
+		case BPF_JMP32 | BPF_JLE | BPF_K:
+		case BPF_JMP32 | BPF_JSGT | BPF_K:
+		case BPF_JMP32 | BPF_JSLE | BPF_K:
+		case BPF_JMP32 | BPF_JSLT | BPF_K:
+		case BPF_JMP32 | BPF_JSGE | BPF_K: {
+			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
 			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 			u8 sreg_lo = IA32_ECX;
 			u8 sreg_hi = IA32_EBX;
+			u32 hi;
 
 			if (dstk) {
 				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
 				      STACK_VAR(dst_lo));
-				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
-				      STACK_VAR(dst_hi));
+				if (is_jmp64)
+					EMIT3(0x8B,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EDX),
+					      STACK_VAR(dst_hi));
 			}
 
-			hi = imm32 & (1<<31) ? (u32)~0 : 0;
 			/* mov ecx,imm32 */
 			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
-			/* mov ebx,imm32 */
-			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
-
-			/* cmp dreg_hi,sreg_hi */
-			EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
-			EMIT2(IA32_JNE, 2);
+			if (is_jmp64) {
+				hi = imm32 & (1 << 31) ? (u32)~0 : 0;
+				/* mov ebx,imm32 */
+				EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+				/* cmp dreg_hi,sreg_hi */
+				EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+				EMIT2(IA32_JNE, 2);
+			}
 			/* cmp dreg_lo,sreg_lo */
 			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));